СРАВНЕНИЕ РЕАЛИЗАЦИЙ ВЫЧИСЛЕНИЯ ВЕКТОРОВ СМЕЩЕНИЯ ВИДЕОИЗОБРАЖЕНИЙ ВО ВСТРАИВАЕМЫХ СИСТЕМАХ

P. A. Ushakov; A. Yu. Pechenkin

doi:10.22213/2410-9304-2019-3-4-115-119

Authors

P. A. Ushakov
A. Y. Pechenkin

DOI:

https://doi.org/10.22213/2410-9304-2019-3-4-115-119

Keywords:

Lucas-Kanade algorithm, feature point tracking, optical flow, image matched filtering

Abstract

Various algorithms of video image displacement vectors calculation are considered. These algorithms are used in smartphones, digital photo cameras, different special-purpose devices in order to stabilize the image, traffic control, air photographic survey, object tracking and other applications. In order to compare the efficiency of hardware resources consumption to perform video images displacement vectors calculation algorithms there were considered: Lucas-Kanade method-based algorithm and the image matched filtering algorithm. Global image displacement was estimated by means of a hardware platform – Ultrascale+ Xilinx SoC. Matrix calculations of the Lucas-Kanade algorithm were performed with four equal hardware blocks, and it made it possible to calculate the displacements of the frames for four points at the same time. The acquired average optical flow calculation time was 7.5 ms. Four hardware blocks were also used to perform parallel calculations to implement the 2D-DFT-based image matched filtering. The resulting operation time of the algorithm was 2.9 ms, and the CPU time used by the algorithm was 0.2 ms. The implementations revealed weak spots of the algorithms, and the required hardware resources of SoPC were determined. The matching filtering algorithm proved to be more efficient as compared to the Lucas-Kanade algorithm to estimate the video sequence consecutive frames displacement upon enough hardware resources.

References

CHANG T. H. TRACKING MULTIPLE PEOPLE WITH A MULTI-CAMERA SYSTEM / T.H. CHANG, S. GONG // PROCEEDINGS 2001 IEEE WORKSHOP ON MULTI-OBJECT TRACKING. 2001. P. 19-26. DOI:10.1109/MOT.2001.937977.

Pan J. Robust Occlusion Handling in Object Tracking / J. Pan, B. Hu // 2007 IEEE Conference on Computer Vision and Pattern Recognition : Minneapolis, MN, 17 - 22 June 2007; [CVPR 2007; proceedings] ; Vol. 4.

Bewley A. Simple online and realtime tracking / A. Bewley, G. Zongyuan, L. Ott, F. Ramos, B. Upcroft // 2016 IEEE International Conference on Image Pro-cessing (ICIP 2016), Phoenix, Arizona, USA 25-28 September 2016. Pp. 3464-3468.

Волосатова Т. М., Яблоков В. Е. Слежение за выделенными объектами на протяжении видеоряда // Инженерный вестник. 2015. №7. С. 518–531.

Sanjay S., Chandra S., Anil V. Real-Time FPGA-Based Object Tracker with Automatic Pan-Tilt Features for Smart Video Surveillance Systems // J. Imaging 2017, 3, 18; doi:10.3390/jimaging3020018

Peng G., Ruyue Y., Zhicong L., Linsheng Z., Yan Z. A Novel Low-cost FPGA-based Real-time Object Track-ing System // arXiv:1804.05535v2 DOI:10.1109/ASICON.2017.8252560

Baoyan Z., Xiaofeng L., Qiaoyuan W., Siqi Z., Qianyun L. A Hardware Architecture of Target Tracking System on FPGA // Proceedings of the 2nd International Conference on Computer Science and Application Engi-neering 2018. Article No. 65 ISBN: 978-1-4503-6512-3 DOI:10.1145/3207677.3278009.

Milan A. MOT 16: a benchmark for multiobject tracking / A. Milan, L. Leal-Taixe, I. Reid, S. Roth, K. Schindler.// arXiv preprint arXiv:1603.00831 (2016). Pp. 1-12.

Bruce D. An Iterative Image Registration Technique with an Application to Stereo Vision / D. Bruce, Lucas and Takeo Kanade // IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelli-gence. Vol. 2, 1981. Pр. 674-679.

Сакович И. О., Белов Ю. С. Применение метода Лукаса – Канаде для вычисления оптического потока // Инженерный журнал: наука и инновации, 2014, вып. 7. URL: http: // engjournal.ni/catalog/pribor/ optica/1275.html.

Прэтт У. Цифровая обработка изображений / пер. с англ. М. : Мир, 1982. Кн. 2. 480 с.

Bagni В. Demystifying the Lucas-Kanade Optical Flow Algorithm with Vivado HLS / D. Bagni, P. Kannan, S. Neuendorffer: URL: https://www.xilinx.com/ support/documentation/application_notes/xapp1300-lucas-kanade-optical-flow.pdf.

Поляк Б. Т. Метод Ньютона и его роль в оптимизации и вычислительной математике // Труды ИСА РАН. 2006. Т. 28. С. 48–66.

Цифровая обработка изображений в информационных системах: Учебное пособие / И. С. Грузман, В. С. Киричук, В. П. Косых, Г. И. Перетягин, А. А. Спектор. Новосибисрк : Изд-во НГТУ, 2002. 352 c.

Прэтт У. Цифровая обработка изображений / пер. с англ. М. : Мир, 1982. Кн. 2. 480 с.